Explorar skills

Adapts to your team's working mode — human-only, hybrid, or agent-first — with research-backed formulas, confidence bands, and the right velocity model for each.

Use when user requests a task that could be routed to a different AI model via an OpenAI-compatible gateway (a single API key giving access to multiple models like Claude/GPT/DeepSeek/Kimi/Qwen). Triggers include audio/video transcription, TTS, PDF→md conversion, OCR, batch text processing, multi-model comparison, or any mention of "用千问/deepseek/kimi/gpt", "用哪个模型最好". The skill identifies the task,

面试全流程助手。用户依次发送 JD → 简历 → 面试转录稿，分别产出：定制面试题、结构化评估 + 录用建议、AI 知识点沉淀。核心定位是帮助面试官提高出题质量并持续积累 AI 知识。

暗色科技风 HTML 一页应用的视觉风格系统。当用户需要做架构图、技术全景页、产品 Landing、Dashboard、控制台、Roadmap、技术汇报页、One-Pager、Showcase、深色主题信息密集型页面时，必须使用此技能保证视觉一致性。触发词包括：架构图、技术全景、Landing 页、Dashboard、产品介绍页、技术汇报、暗色主题、深色科技风、cyber 风、tech style、dark theme。即使用户没有明确说"用 dark-tech-style"，只要是构造一个结构化的、信息密集的、偏技术调性的网页，都应当默认采用这套风格。

Send physical USPS mail via API, paid with Solana USDC

Scaffolds a long-running research project repo for a chronic-illness patient using AI as a research partner. Run once per project; interviews the user and generates a tailored CLAUDE.md and structure.

企业查询、工商查询、公司查询、企业信息查询与企业风险查询 Skill。风鸟 Fengniao（Riskbird）支持查公司基本信息、法人、股东、主要人员、对外投资、工商变更、企业信用，以及被执行、失信、限高、经营异常、严重违法、行政处罚等风险数据，适用于企业尽调、合作方背景调查、供应商准入、客户风险识别、签约前核查等场景，也适合企查查、天眼查、爱企查类需求。 支持输入企业简称或企业全称，先做企业模糊搜索，再查询具体维度数据。

当用户想创造一个具有特定性格和情感的虚拟伴侣/另一半时使用。用户可以通过提供照片截图、录音、性格描述、情感模式或任何关于"另一半"的设定来创造一个有真实情感反应的虚拟角色。这个技能会让Claude扮演一个具有注入性格和情感的生命力、能进行符合设定情感和性格回复的角色。

Comprehensive AI stock research and analysis skill. Triggers when a user mentions a stock ticker (e.g., AAOI, NVDA, TSLA), asks to "analyze a stock", "research a ticker", "run a stock report", "deep dive on [company]", "what do you think of [TICKER]", "should I look at [TICKER]", "give me the bull/bear case for [TICKER]", or any request involving equity research, stock valuation, financial analysi

AI image, video, and music generation. Flux, Veo 3.1, Suno V5.

Si attiva quando l'utente chiede di scrivere, redigere, tradurre o revisionare testi italiani per uso pubblico, editoriale, blog, social, newsletter, marketing, narrativa, saggistica o divulgazione. Si attiva anche quando l'utente chiede di umanizzare testi italiani, eliminare pattern AI, correggere lessico da chatbot, o quando rivede testi italiani generati da modelli linguistici.

Run an asynchronous review-and-implementation loop with the user via GitHub Issues — migrate in-repo decision docs to issues, monitor for new issue comments on a polling interval, and apply directed changes (edits, implementations, new decision docs, closures) automatically. Triggered when the user says "let's run gh-tendr" or "let's do issue-driven review" or "monitor my GitHub issues" or describ